© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 792
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to social-opening words and interjections (greetings, thanks, apologies, exclamations) like “Hello,” “Thanks,” or “Sorry.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     வழிபட்டால்
    0.55
    它的
    0.46
    たと
    0.43
    imis
    0.42
    이는
    0.41
    Location
    0.41
    就
    0.41
    個
    0.41
    它可以
    0.41
    gradle
    0.41
    POSITIVE LOGITS
    ،
    0.61
     ك
    0.55
     ،
    0.55
     يا
    0.52
    ண்ட்
    0.50
     シャネル
    0.50
     पण
    0.49
     lanjut
    0.49
     yah
    0.49
    !...
    0.49
    Activations Density 0.083%

    No Known Activations